DeepMind makes bet on AI system that can play poker, chess, Go, and more
DeepMind, the AI lab backed by Google parent company Alphabet, has long invested in game-playing AI systems. It’s the lab’s philosophy that games, while...
DeepMind’s MuZero picks up the rules of games as it plays
In a paper published in the journal Science late last year, Google parent company Alphabet’s DeepMind detailed AlphaZero, an AI system that could teach itself...
DeepMind’s AI automatically generates reinforcement learning algorithms
In a study published on the preprint server Arxiv.org, DeepMind researchers describe a reinforcement learning algorithm-generating technique that discovers what to predict and how...
DeepMind’s AI studies game players to exploit weaknesses in their strategies
In a paper published on the preprint server Arxiv.org, scientists at Alphabet’s DeepMind propose a new framework that learns an approximate best response to players within games...
DeepMind’s Agent57 beats humans at 57 classic Atari games
In a preprint paper published this week by DeepMind, Google parent company Alphabet’s U.K.-based research division, a team of scientists describe Agent57, which they...
DeepMind technique encourages AI players to cooperate in zero-sum games
In a preprint paper, DeepMind described a new reinforcement learning technique that models human behavior in a potentially new and powerful way. It could...
DeepMind’s Dreamer AI learns from the past to predict the future
Some AI systems achieve goals in challenging environments by drawing on representations of the world informed by past experiences. They generalize these to novel...
DeepMind’s MuZero teaches itself how to win at Atari, chess, shogi, and Go
In a paper published in the journal Science late last year, Google parent company Alphabet’s DeepMind detailed AlphaZero, an AI system that could teach...
BlizzCon fans will be able to battle DeepMind’s AI in StarCraft 2
Google’s DeepMind artificial intelligence program AlphaStar will battle attendees at BlizzCon 2019 in matches of the classic Blizzard real-time strategy game StarCraft 2. In...
DeepMind’s AlphaStar Final beats 99.8% of human StarCraft 2 players
Alphabet subsidiary DeepMind — which famously developed AlphaZero, a machine learning system that bested world champions in chess, shogi, and Go — returned to...